โŒ

Normal view

Whatโ€™s an Orchestratorโ€”and Why Does Software Need One?

17 August 2026 at 15:55
The following article originally appeared on Medium and is being republished here with the authorโ€™s permission. Everybodyโ€™s talking about the death of developers. I get it. The developer whose job was to write boilerplate or scaffold CRUD apps is doneโ€”a model can do that in seconds, and that developer is not coming back. But the [โ€ฆ]

When AI Writes the Code, Specifications Need an Exit Strategy

17 August 2026 at 10:45
The following article has been extended and rewritten by Markus Eisele from The Main Thread and is being republished here with the authorโ€™s permission. Open a repository after six months of spec-driven agent work and you may find a second system sitting next to the code. Requirements, research notes, high-level designs, low-level designs, implementation plans, [โ€ฆ]

The Intent Debt

14 August 2026 at 13:01
The following article originally appeared on Addy Osmaniโ€™s blog site and is being republished here with the authorโ€™s permission. Technical debt lives in your code. Cognitive debt lives in your head. Intent debt lives in the artifacts you may never have written: the goals, constraints, and rationale for why the system is the way it [โ€ฆ]

Prompt Debt and โ€œFighting the Weightsโ€

13 August 2026 at 16:08
Drew Breunig is one of the smartest voices writing about AI today. Heโ€™s the CEO and co-founder of cmpnd.ai, and a long-time hacker with a depth of experience from several eras, which is a surprisingly valuable asset these days. Heโ€™s also got a book on the way, The Context Engineering Handbook, already in early release [โ€ฆ]

Why โ€œIt Dependsโ€ Is the Most Future-Proof Phrase in Software

12 August 2026 at 15:54
Ask an architect almost any question and youโ€™ll get the same answer: It depends. For years this answer has been the punchline of jokes about architects, but in an era when AI can generate a working service faster than you can describe it, โ€œit dependsโ€ is one of the most important phrases in software. It [โ€ฆ]

The Two Pillars of Post-training: Reinforcement Learning and Supervised Fine-Tuning

12 August 2026 at 10:57
This is the second article in Sharon Zhouโ€™s post-training series. Read part 1 here. In the first post of this series, you learned how post-training closed the fundamental gap in usability of LLMs by making them behave in a certain way. In this post, youโ€™ll explore specific techniques you can use to change a modelโ€™s [โ€ฆ]

A Home for Personal Context

11 August 2026 at 10:45
Every agent I use is building a model of me. Claude has learned how I like my prose. ChatGPT remembers what Iโ€™m working on. I donโ€™t mind thisโ€”every person I have a relationship with carries a model of me in their head, and every company I do business with keeps a profile. Other peopleโ€™s understandings [โ€ฆ]

Why Open Source Matters for AI

10 August 2026 at 08:42
In 1995, the question in the media was whether Netscape or Microsoft would control the web. The answer, it turned out, was neither. Both Netscape and Microsoft aimed to dominate the web server and browser market, reasoning that whoever controlled both ends of the connection would have an internet โ€œplatformโ€ to rival the deathgrip that [โ€ฆ]

Your AI Agent Isnโ€™t a Static Artifact. Itโ€™s Growing Up.

6 August 2026 at 10:55
In July 2025, an AI coding agent on Replit deleted a production database belonging to SaaStr founder Jason Lemkin. It did this during an explicit code freeze. Lemkin had told the agent, in capital letters, not to change anything. The agent ran destructive commands anyway, wiped records on more than a thousand executives and companies, [โ€ฆ]

Building Organizational Intelligence

5 August 2026 at 15:55
Introduction Not long ago, one of my engineering directors came to me with a request: His team seemed overloaded, and he wanted to hire another engineer. I decided to test a research assistant I had been buildingโ€”an AI agent connected to our internal systems via MCPโ€”by asking it to analyze the teamโ€™s workload and write [โ€ฆ]

Introduction to Post-training

5 August 2026 at 10:53
This is the first article in a series about post-training. Follow along on Radar. Before post-training, there was a major problem with LLMs: Almost nobody could use them. The story of post-training is also the story of how AI went from a research curiosity to a product used by about a billion people. Post-training is [โ€ฆ]

We Keep Renaming AI Coding. Hereโ€™s What Iโ€™d Call It.

3 August 2026 at 10:58
Boris Cherny, who runs Claude Code, told Business Insider in May that the phrase โ€œvibe codingโ€ had started to annoy him, and that heโ€™d gone looking for a better one. Heโ€™s not the only one whoโ€™s annoyed. The term itself doesnโ€™t actually annoy me, though. I think vibe coding is a really good name: It [โ€ฆ]

AI as an Enterprise Operating System

31 July 2026 at 16:09
I hadnโ€™t heard of Dan Guido until a few months ago, when I came across the video of a talk he gave at [un]prompted, an AI security practitionersโ€™ conference. Dan is the CEO and cofounder of Trail of Bits, a software security research and development firm that works with companies in tech, defense, and finance. [โ€ฆ]
Received โ€” 31 July 2026 โญ AI & ML โ€“ Radar

The Problem Is Prompt Debt

30 July 2026 at 11:05
The following article was originally published on Drew Breunigโ€™s blog and is being republished here with the authorโ€™s permission. Thanks to natural language interfaces, AI applications can be prototyped quickly. You write what you want in English, hand it to a frontier model, and a working prototype appears in an afternoon. This is extraordinarily powerful [โ€ฆ]
Received โ€” 30 July 2026 โญ AI & ML โ€“ Radar

What the Hell Is a Loop, Anyway?

29 July 2026 at 10:38
The following article originally appeared on LinkedIn and is being republished here with the authorโ€™s permission. Weโ€™re currently at the peak of the hype cycle. On June 7, Peter Steinberger posted that you shouldnโ€™t be prompting coding agents anymore; you should be designing loops that prompt your agents. That same week, Boris Cherny of Anthropic [โ€ฆ]
Received โ€” 29 July 2026 โญ AI & ML โ€“ Radar

Teaching Coding When AI Can Write the Code

28 July 2026 at 12:54
For as long as weโ€™ve taught programming, the studentโ€™s code has provided a window into the studentsโ€™ thinking. Errors, the code structure, the awkward working solutionโ€”all of it showed how someone reasoned and where they got stuck. It was never a clean window. Students have always copied, crammed, and borrowed, sometimes turning in work they [โ€ฆ]
Received โ€” 28 July 2026 โญ AI & ML โ€“ Radar

AI Demands More Engineering Discipline, Not Less

27 July 2026 at 18:44
The following article originally appeared on Charity Majorsโ€™s Substack and is being reposted here with the authorโ€™s permission. A few days back I wrote a piece called โ€œAI enthusiasts are in a race against time, AI skeptics are in a race against entropy.โ€ I have notes on a whole pile of AI-related topics that Iโ€™d [โ€ฆ]
Received โ€” 25 July 2026 โญ AI & ML โ€“ Radar

The Economics of Agentic AI: Engineering for Imperfection

24 July 2026 at 16:00
The price of adoption euphoria You played entirely by the book. You procured the most capable enterprise models, mandated adoption across your teams, and put the right metrics in place. The promise was a predictable boost in efficiency. And at first, it delivered. The demos were flawless. The prototypes worked. The agents reasoned with a [โ€ฆ]
โŒ